© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39580
    Prev
    Next
    INDEX
    Explanations

    `Sch` followed by `blood`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -0.07
    åīĩ
    -0.07
    åĪĻ以
    -0.06
    åĪĻ
    -0.06
    7
    -0.06
    åıĪæľī
    -0.06
    Extras
    -0.06
    ile
    -0.06
    ÃŃ
    -0.06
    ingo
    -0.06
    POSITIVE LOGITS
    etat
    0.08
    ÑĤеа
    0.08
    doa
    0.08
     Firstly
    0.08
    hluk
    0.08
    pcf
    0.08
    .au
    0.08
    zit
    0.07
    errat
    0.07
    /Dk
    0.07
    Activations Density 0.010%

    No Known Activations